[Sommaire] [Imprimer]

   1  # Rules related to cyrillic
   2  #
   3  # The following charsets uses characters from cyrillic:
   4  # koi-8, koi-8r, iso-8859-5, cp932, cp866, cp855, windows-1251
   5  #
   6  # See basic.tr for formatting options
   7  
   8  # Transliteration of cyrillic, is used in URLs and identifiers
   9  
  10  cyrillic_uppercase:
  11  U+0450 - U+045F      - U+0050
  12  U+0430 - U+044F      - U+0020
  13  
  14  U+0461 - U+0481 % 02 - U+0001
  15  U+048B - U+04BF % 02 - U+0001
  16  U+04C2 - U+04CC % 02 - U+0001
  17  U+04D1 - U+04F5 % 02 - U+0001
  18  
  19  # Cyrillic Supplementary
  20  U+0501 - U+050F % 02 - U+0001
  21  
  22  cyrillic_lowercase:
  23  U+0400 - U+040F      + U+0050
  24  U+0410 - U+042F      + U+0020
  25  
  26  U+0460 - U+0480 % 02 + U+0001
  27  U+048A - U+04BE % 02 + U+0001
  28  U+04C1 - U+04CD % 02 + U+0001
  29  U+04D0 - U+04F4 % 02 + U+0001
  30  
  31  # Cyrillic Supplementary
  32  U+0500 - U+050E % 02 + U+0001
  33  
  34  cyrillic_diacritical:
  35  # Cyrillic extension
  36  U+0400 - U+0401 = U+0415
  37  U+0403 = U+0413
  38  U+0407 = U+0406
  39  U+040C = U+041A
  40  U+040D = U+0418
  41  U+040E = U+0423
  42  
  43  # Basic russian
  44  U+0419 = U+0418
  45  U+0439 = U+0438
  46  
  47  # Cyrillic extension
  48  U+0450 = U+0435
  49  U+0451 = U+0435
  50  U+0453 = U+0433
  51  U+0457 = U+0456
  52  U+045C = U+043A
  53  U+045D = U+0438
  54  U+045E = U+0443
  55  
  56  # Historic letters
  57  U+0476 = U+0474
  58  U+0477 = U+0475
  59  
  60  # Extended cyrillic
  61  U+04C1 = U+0416
  62  U+04C2 = U+0436
  63  U+04D0 = U+0410
  64  U+04D1 = U+0430
  65  U+04D2 = U+0410
  66  U+04D3 = U+0430
  67  U+04D6 = U+0415
  68  U+04D7 = U+0435
  69  U+04DA = U+04D8
  70  U+04DB = U+04D9
  71  U+04DC = U+0416
  72  U+04DD = U+0436
  73  U+04DE = U+0417
  74  U+04DF = U+0437
  75  U+04E2 = U+0418
  76  U+04E3 = U+0438
  77  U+04E4 = U+0418
  78  U+04E5 = U+0438
  79  U+04E6 = U+041E
  80  U+04E7 = U+043E
  81  U+04EA = U+04E8
  82  U+04EB = U+04E9
  83  U+04EC = U+042D
  84  U+04ED = U+044D
  85  U+04EE = U+0423
  86  U+04EF = U+0443
  87  U+04F0 = U+0423
  88  U+04F1 = U+0443
  89  U+04F2 = U+0423
  90  U+04F3 = U+0443
  91  U+04F4 = U+0427
  92  U+04F5 = U+0447
  93  U+04F8 = U+042B
  94  U+04F9 = U+044B
  95  
  96  cyrillic_transliterate_ascii:
  97  U+0400 = "IE"
  98  U+0401 = "IO"
  99  U+0402 = "D"
 100  U+0403 = "G"
 101  U+0404 = "IE"
 102  U+0405 = "DS"
 103  U+0406 = "II"
 104  U+0407 = "YI"
 105  U+0408 = "J"
 106  U+0409 = "LJ"
 107  U+040A = "NJ"
 108  U+040B = "Ts"
 109  U+040C = "KJ"
 110  U+040D = "I"
 111  U+040E = "V"
 112  U+040F = "DZ"
 113  
 114  U+0410 = "A"
 115  U+0411 = "B"
 116  U+0412 = "V"
 117  U+0413 = "G"
 118  U+0414 = "D"
 119  U+0415 = "E"
 120  U+0416 = "ZH"
 121  U+0417 = "Z"
 122  U+0418 = "I"
 123  U+0419 = "J"
 124  U+041A = "K"
 125  U+041B = "L"
 126  U+041C = "M"
 127  U+041D = "N"
 128  U+041E = "O"
 129  U+041F = "P"
 130  
 131  U+0420 = "R"
 132  U+0421 = "S"
 133  U+0422 = "T"
 134  U+0423 = "U"
 135  U+0424 = "F"
 136  U+0425 = "H"
 137  U+0426 = "C"
 138  U+0427 = "CH"
 139  U+0428 = "SH"
 140  U+0429 = "SCH"
 141  U+042A = "\'"
 142  U+042B = "Y"
 143  U+042C = "\'"
 144  U+042D = "E"
 145  U+042E = "YU"
 146  U+042F = "YA"
 147  
 148  U+0430 = "a"
 149  U+0431 = "b"
 150  U+0432 = "v"
 151  U+0433 = "g"
 152  U+0434 = "d"
 153  U+0435 = "e"
 154  U+0436 = "zh"
 155  U+0437 = "z"
 156  U+0438 = "i"
 157  U+0439 = "j"
 158  U+043A = "k"
 159  U+043B = "l"
 160  U+043C = "m"
 161  U+043D = "n"
 162  U+043E = "o"
 163  U+043F = "p"
 164  
 165  U+0440 = "r"
 166  U+0441 = "s"
 167  U+0442 = "t"
 168  U+0443 = "u"
 169  U+0444 = "f"
 170  U+0445 = "h"
 171  U+0446 = "c"
 172  U+0447 = "ch"
 173  U+0448 = "sh"
 174  U+0449 = "sch"
 175  U+044A = "\'"
 176  U+044B = "y"
 177  U+044C = "\'"
 178  U+044D = "e"
 179  U+044E = "yu"
 180  U+044F = "ya"
 181  
 182  U+0450 = "ie"
 183  U+0451 = "io"
 184  U+0452 = "dj"
 185  U+0453 = "g"
 186  U+0454 = "e"
 187  U+0455 = "z"
 188  U+0456 = "i"
 189  U+0457 = "yi"
 190  U+0458 = "j"
 191  U+0459 = "lj"
 192  U+045A = "nj"
 193  U+045B = "c"
 194  U+045C = "kj"
 195  U+045D = "i"
 196  U+045E = "v"
 197  U+045F = "dz"
 198  
 199  cyrillic_search_cleanup:
 200  # Turns some special characters into spaces
 201  U+0482 - U+0486 = U+0020
 202  U+0488 - U+0489 = U+0020